Neurocomputing

A mean field model (MFM) is a mesoscopic description of neuronal population dynamics that can reduce the complexity of neural microcircuits into equations preserving key functional properties. The generation of a MFM is a complex mathematical process that starts with the incorporation of single neuron input/output relationships and local connectivity. Once neuron electroresponsiveness and synaptic properties are defined, in principle, the process can be automatized. Here we develop a tool for automatic MFM derivation from biophysically grounded spiking networks (Auto-MFM) by performing micro-to-mesoscale parameter remapping, estimating input/output relationships specific for different neuronal populations (i.e., transfer functions), and optimizing transfer function parameters. Auto-MFM was tested using a spiking cerebellar circuit as a generative model. The cerebellar MFM derived with Auto-MFM accurately reproduced cerebellar population dynamics of the corresponding spiking network, matching mean and time-varying firing rates across a wide range of stimulation patterns. Auto-MFM allowed us to model and explore physiological and pathological circuit variants; indeed, it was used to map ataxia-related structural connectivity alterations of the cerebellar network, in which Purkinje cells with simplified dendritic structure altered the cerebellar connectivity. Furthermore, Auto-MFM was used to create a library of cerebellar MFMs by sweeping the level of the excitatory conductance at mossy fiber - granule cell synapse, which is altered in several neuropathologies. Auto-MFM is thus proving a flexible and powerful tool to generate region-specific MFMs of healthy and pathological brain networks to be embedded in brain digital models.

AO_SCPLOWBSTRACTC_SCPLOWOne of the most compelling ideas for bridging neuroscience and artificial neural networks is the establishment of a framework based on three main components: network architecture, optimization mechanism, and loss (or objective) function to be minimized. While the first two components have been extensively explored, the definition of a loss or objective function in neuroscience has been addressed less thoroughly, often from perspectives such as predictive coding. In this work, we propose an elementary loss function grounded in the comparison of neuronal responses to two signals: an external one, used for learning, and an internal one, reflecting the acquired knowledge. The loss function is thus simply the basic difference between the two, which, in terms of logical signals, corresponds to a well-known non-linearly separable function: the XOR function. We illustrate with a computational example how a binarized image recognition algorithm can be straightforwardly implemented in an autoencoder, and we show how a neuronal motif organized around an inhibitory neuron could implement such XOR operation and provide a feedback signal that makes optimization possible.

Hippocampus is known to replay activity patterns to recall and process memories, which is often related to Hopfield-type attractor dynamics. Another line of theoretical studies suggests that hippocampal replay prioritizes replay of experiences to accelerate value learning for efficient decision making. It is unknown how hippocampal attractor dynamics perform prioritized memory sampling, and more broadly, how we can consistently relate dynamical (bottom-up) and functional (top-down) theories of hippocampal replay. In this paper, we propose an extended Hopfield-type attractor network model with momentum, kinetic energy, and conservation of the total energy, which is called momentum Hopfield model. We show that our model can be interpreted as CA3-CA1 network model with intrinsic oscillation, and such network model reproduces hippocampal replay in 1-D and 2-D spatial structures. We also prove that our model functionally works as Markov-chain Monte Carlo sampling in which recall frequencies of memory patterns can be arbitrarily biased. Using this property, we implemented prioritized experience replay using our model, which actually accelerated reinforcement learning for spatial navigation. Our model explains how dynamics of hippocampal circuits realize efficient memory sampling, providing a theoretical link between dynamics and functions of hippocampal replay.

Neurons in the cerebral cortex are organized topographically. In the primate visual cortex, neighboring neurons often respond to similar stimulus parameters, such as receptive field position, orientation, color, and spatial frequency. Preferred stimulus parameters change smoothly across the cortical surface. If such topographic organization plays an important role in computation, it is likely to emerge in artificial neural networks. In this study, a multistream convolutional neural network was constructed in which filters in the first convolutional layer were arranged in a two-dimensional filter matrix according to their output connections. The network was trained using supervised learning for image classification. Although adjacent filters in the filter matrix can develop any structure in principle, they acquire similar degrees of orientation and color selectivity. Moreover, they prefer similar orientations, hues, and spatial frequency. The similarity decreases with distance between filters in the matrix. Furthermore, neural-network model instances that have a strong relationship between filter distance and filter-property similarity performed better than those with a weak relationship. These results suggest that topographic organization emerges spontaneously in an artificial neural network and plays an important role in model performance, suggesting the importance of topographic organization for computations performed by artificial and biological neural networks.

Brain tumors are one of the most life-threatening diseases, requiring precise and timely detection for effective treatment. Traditional methods for brain tumor detection rely heavily on manual analysis of MRI scans, which is time-consuming, subjective, and prone to human error. With advancements in deep learning, Convolutional Neural Networks (CNNs) have become popular for medical image analysis. However, CNNs are limited in their ability to capture spatial hierarchies and pose variations, which reduces their accuracy, particularly for tasks like brain tumor segmentation where precise spatial relationships are crucial. This research introduces a hybrid Capsule Neural Network (CapsNet) and ResNet50 model designed to overcome the limitations of traditional CNNs by capturing both spatial and pose information in MRI scans. The proposed model leverages ResNet50 for feature extraction and CapsNet for handling spatial relationships, leading to more accurate segmentation. The study evaluates the model on the BraTS2020 dataset and compares its performance to state-of-the-art CNN architectures, including U-Net and pure CNN models. The hybrid model, featuring a custom 5-cycle dynamic routing algorithm to enhance capsule agreement for tumor boundaries, achieved 98% accuracy and an F1-score of 0.87, demonstrating superior performance in detecting and segmenting brain tumors. This study pioneers the systematic evaluation of the ResNet50 + CapsNet hybrid on the BraTS2020 dataset, with a tailored class weighting scheme addressing class imbalance, improving effectiveness in identifying irregularly shaped tumors and smaller regions in identifying irregularly shaped tumors and smaller tumor regions. The study offers a robust solution for automating brain tumor detection. Future work will explore the use of Capsule Networks alone for brain tumor detection in MRI data and investigate alternative Capsule Network architectures, as well as their integration into clinical decision support systems.

As social beings, humans make decisions partly based on social interaction. Observing the behavior of others can lead to learning from and about them, potentially increasing trust and prompting trust-based behavioral changes. Observation-based decision making involves different neural structures. The orbitofrontal cortex (OFC) and lateral prefrontal cortex (LPFC) are known as neural structures mainly involved in processing emotional and cognitive decision values, respectively, while the anterior cingulate cortex (ACC) plays a pivotal role as a social hub, integrating the afferent expectancy signals from OFC and LPFC. This paper presents a neurocomputational model of the interplay between observational learning and trust, as well as their role in individual decision-making. Our model elucidates and predicts the emotional and rational behavioral changes of an individual influenced by observing the action-outcome association of an alleged expert. We have modeled the neurodynamics of three cortical structures (OFC, LPFC, and ACC) and their interactions, where the neural oscillatory properties, modeled with Dynamic Bayesian Probability, represent the observers attitude towards the expert and the decision options. As an example of an everyday behavioral situation related to climate change, we use the choice of transportation between home and work. The EEG-like simulation outputs from our model represent the presumed brain activity of an individual making such a choice, assuming the decision-maker is exposed to social information.

Computer vision and deep learning techniques, including convolutional neural networks (CNNs) and transformers, have increased the performance of medical image classification systems. However, training deep learning models using medical images is a challenging task that necessitates a substantial amount of annotated data. In this paper, we implement data augmentation strategies to tackle dataset imbalance in the VinDr-SpineXR dataset, which has a lower number of spine abnormality X-ray images compared to normal spine X-ray images. Geometric transformations and synthetic image generation using Generative Adversarial Networks are explored and applied to the abnormal classes of the dataset, and classifier performance is validated using VGG-16 and InceptionNet to identify the most effective augmentation technique. Additionally, we introduce a hybrid augmentation technique that addresses class imbalance, reduces computational overhead relative to a GAN-only approach, and achieves ~99% validation accuracy with both classifiers across all three case studies. Keywords: Data augmentation, Generative Adversarial Network, VGG-16, InceptionNet, Class imbalance, Computer vision, Spine X-ray, Radiology.

The impact of cellular activities on large-scale brain dynamics is thought to determine brain functioning and disease, yet the causal relationships of neural mechanisms across scales remain unclear. Recently, the cerebellum has been reported to affect whole-brain dynamics during sensorimotor integration. To disclose the underlying mechanisms, we have developed a multiscale digital brain co-simulator, in which a spiking neural network of the olivo-cerebellar microcircuit is embedded in a mouse virtual brain and wired with other nodes using an atlas-based long-range connectome. Parameters and bi-directional interfaces between the spiking olivo-cerebellar network and other rate-coded modules were tuned to match experimental data of primary sensory and motor cortex (M1 and S1) power spectral densities and neuronal spiking rates. Then, the role of the cerebellar circuitry on sensorimotor integration was analyzed by lesioning critical circuit connections in silico. Simulations showed that spike processing within the cerebellar circuit is key to explaining the gamma-band coherence between M1 and S1 during sensorimotor integration. These results provide a mechanistic explanation of how the cerebellum promotes the formation of sensorimotor contingencies in relevant cortical modules as the basis of its critical role in sensorimotor prediction. On a broader perspective, this modelling approach opens new perspectives for the multiscale investigation of brain physiological and pathological states in relation to specific cellular and microcircuit properties.

Alzheimers disease (AD) is a devastating neurodegenerative disease whose etiology is poorly understood and for which current treatments provide only modest control of symptoms. To better investigate the causes and progression of the disease, the transgenic TgF344-AD rat model has emerged as a crucial tool. In this paper, we collect observations on the accumulation of amyloid-{beta}, changes in neuronal density, and a decline in cognitive performance in TgF344-AD and wild-type rats. We develop a compartmental ordinary differential equation model and determine its parameters by fitting the output to the experimental observations. Our model simulations support the hypothesis that the accumulation of amyloid-{beta} leads to a rapid decline in neuronal density followed by a significant loss in memory and learning ability. Our mathematical model can provide a bridge between AD research in rodent models and the human condition of AD.

Network analysis of human brain connectivity provides a fundamental framework for identifying the neurobiological mechanisms that cause cognitive variations and neurological disorders. However, existing diagnostic models often treat structural connectivity (SC) as a fixed or optimal topological scaffold for functional connectivity (FC). This consequently overlooks the higher-order dependencies between brain regions that are critical for characterizing pathological alterations. Moreover, the distinct spatial organizations of SC and FC complicate their direct integration, as naive alignment methods may distort the inherent nonlinear patterns of brain connectivity. To address these limitations, we propose the Graph Diffusion Optimal Transport Network (GDOT-Net), which models disease-related topological evolution and achieves precise alignment between SC and FC. Unlike existing diffusion studies, the proposed model introduces an evolvable brain connectome modeling approach to infer the complex topological structure of brain networks, unveiling higher-order connectivity patterns linked to specific neuropsychiatric disorders. Furthermore, GDOT-Net incorporates a Pattern-Specific Alignment mechanism, leveraging optimal transport to align structural and functional topological representations in a geometry-aware manner. To capture nonlinear topological relationships between brain regions, a Neural Graph Aggregator Module was developed, which adaptively learns complex node interaction patterns in brain networks. By leveraging this module, GDOT-Net generates highly discriminative representations that form a robust basis for the precision diagnosis of brain disorders. Experiments on REST-meta-MDD and ADNI demonstrate that GDOT-Net surpasses SOTA methods in uncovering structural-functional misalignments and disorder-specific subnetworks. The source code is publicly available at this Link.

The main challenges in the life of a child with autism are difficulties in communication, behavior, and social interaction. Early diagnosis of this neurodevelopmental disorder improves patient outcomes by enabling more effective, personalized interventions. This diagnosis can sometimes be difficult, especially in very young children. Non-invasive, relatively accessible, and able to reflect neural function in real time, electroencephalography (EEG) shows promise in the detection of Autism spectrum disorders (ASD). However, because EEG data is still difficult for experts to understand, machine learning and artificial intelligence (AI) are beginning to be used in this field as well. In this paper, a ResNet+BiLSTM hybrid deep network was applied and achieved high accuracy in distinguishing individuals with autism from neurotypical subjects. Since AI models typically provide predictions without clear explanations, this study employs explainable AI (XAI) methods such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to clarify their decision-making.Delta, theta, alpha, beta, and gamma waves, as well as ERP components P100, N100, P200, MMN, and P600, were analyzed in the two neurotypical and autistic groups that were compared in this study using EEG recordings. By integrating SHAP and LIME, the system achieved both accurate classification and transparent explanations, pointing to EEG- and ERP-based features as reliable biomarkers for ASD.

A central objective in neuroscience is to elucidate how the brain generates complex dynamic activity through the interactions of brain areas. In this study, we utilized Interaction Network, a graph neural network model, to develop a computational framework for predicting whole-brain cortical blood oxygenation level dependent (BOLD) signals. We derived an Inter-Regional Interaction (IRI) metric to quantify information exchange among brain areas probing the underlying dynamical mechanisms. In addition, the total IRI emitted from each brain region was calculated and defined as the IRI sent by region (RS-IRI). Our model predicted the following 10 time points BOLD activity from initial BOLD signals, and achieved a mean absolute error of 0.04. The predicted functional connectivity (FC) achieves a correlation coefficient of 0.97 compared to the empirical FC. The fluctuation amplitude of the IRI increases with the length of the connection and the largest RS-IRI oscillation amplitude is observed in visual areas. The RS-IRI demonstrates a hierarchical organization, characterized by more concentrated distributions in association regions and larger fluctuation amplitudes in unimodal regions. Applying our approach to Alzheimers disease (AD), we demonstrate that the frequency-specific amplitudes of IRI oscillations discriminate AD patients from healthy controls and correlate with Mini-Mental State Examination scores. Together, this work presents a deep learning-based framework for modeling brain dynamics as well a quantitative index of inter-areal interactions, and offers a new perspective for disease characterization. Author SummaryThe human brain comprises distinct regions that interact through complex fiber tracts, forming the functional dynamics for diverse cognitive processes. We employed fMRI to assess functional activity and DTI to reconstruct fiber tract connectivity. To elucidate how brain function emerges from these inter-regional interactions, we developed a novel computational framework based on Graph Neural Network (GNN) to model the brains interactive dynamics for its capacity to uncover hidden and intricate patterns within data. From this model, we derived a quantitative metric termed Inter-Regional Interaction (IRI), which characterized the fine-grained, dynamic fluctuations in communication between brain areas. Our results suggest that this GNN-based model can accurately simulate brain functional activity and provide a quantitative description of neural interaction patterns. Applying this model to a cohort of Alzheimers disease patients, we demonstrated that the IRI metric not only effectively distinguished patients from healthy controls but also significantly correlated with clinical cognitive performance (MMSE scores). This approach advances our understanding of the fundamental principles of brain function and offers a promising tool for identifying the underlying mechanisms of neurological disorders.

Synchrony is a key mechanism that builds up the foundations of human interactions. Quantifying the level of physiological synchronization that occurs during dyadic exchanges is essential to fully comprehend social phenomena. We present a new index to characterize the coupling of complex physiological dynamics: the optimized Multichannel Complexity Index (opMCI). We validated this approach using synthetic time series of two coupled Henon Maps, with four different coupling levels in unidirectional and bidirectional manners. We demonstrated that the opMCI method allows to effectively discern between all coupling levels. Then, we applied the opMCI metric on heart rate variability data collected from 37 parent-infant dyads, during shared reading and playing activities, in the framework of the Shared Emotional Reading (SHER) project, with the aim of assessing the effects of early intervention in preterm babies. Two groups presented preterm infants: an intervention group, who participated in a two-month shared reading program, and a control group, who practiced shared play activities. A full-term group provided additional control data. The opMCI values were significantly higher for the intervention dyads with respect to the other groups during the shared reading task, showing that an early reading intervention program could increase parent-infant synchrony in preterm babies.

Generalization is a fundamental criterion for evaluating learning effectiveness, a domain where biological intelligence excels yet artificial intelligence continues to face challenges. In biological learning and memory, the well-documented spacing effect shows that appropriately spaced intervals between learning trials can significantly improve behavioral performance. While multiple theories have been proposed to explain its underlying mechanisms, one compelling hypothesis is that spaced training promotes integration of input and innate variations, thereby enhancing generalization to novel but related scenarios. Here we examine this hypothesis by introducing a bio-inspired spacing effect into artificial neural networks, integrating input and innate variations across spaced intervals at the neuronal, synaptic, and network levels. These spaced ensemble strategies yield significant performance gains across various benchmark datasets and network architectures. Biological experiments on Drosophila further validate the complementary effect of appropriate variations and spaced intervals in improving generalization, which together reveal a convergent computational principle shared by biological learning and machine learning.

Abstract Objectives: To develop and evaluate a deployable deep learning system with Gradient-weighted Class Activation Mapping (Grad-CAM) for tuberculosis screening from chest radiographs and to assess its classification performance and explainability across desktop and mobile deployment platforms. Materials and methods: This study used publicly available chest X-ray datasets containing Normal and Tuberculosis images. A DenseNet121-based transfer learning model was trained using stratified training, validation, and test splits with data augmentation and class weighting. Model performance was evaluated using accuracy, precision, recall, F1 score, receiver operating characteristic (ROC) curve, and area under the ROC curve (AUC). Grad-CAM was used to visualize regions influencing model predictions. The trained model was converted to TensorFlow Lite and deployed in both a Windows desktop application and a Flutter-based mobile application for offline inference and visualization. Results: The model demonstrated strong classification performance on the independent test dataset, with high accuracy and AUC values indicating effective discrimination between Normal and Tuberculosis cases. Grad-CAM visualizations showed that the model focused primarily on anatomically relevant lung regions, particularly the upper and mid-lung fields in Tuberculosis cases. Deployment testing confirmed consistent prediction outputs and Grad-CAM visualizations across both Windows and mobile platforms. Conclusion: The proposed deployable deep learning system with Grad-CAM provides accurate and interpretable tuberculosis screening from chest radiographs and demonstrates feasibility for offline mobile and desktop deployment. This approach has potential as an artificial intelligence-assisted screening and decision support tool in radiology, particularly in resource-limited and remote healthcare settings.

The present study evaluates the real-world clinical predictive performance of FDA-authorized artificial intelligence (AI) devices used in radiology, focusing on the false positive paradox (FPP) and its implications for clinical practice. To do this, we analyzed publicly available FDA data on AI radiology devices from 2024 and 2025 from 510(k) summaries, demonstrating how diagnostic accuracy metrics like sensitivity and specificity do not necessarily translate into high positive predictive value (PPV) due to the influence of target disease prevalence. We show the importance of disclosing the false discovery (FDR) and false omission rates (FOR) and argue that this transparency enables clinicians to select AI systems that balance false positive and false negative costs in a clinically, ethically, and financially appropriate manner. Finally, we provide recommendations for what data should be provided to best serve practices and radiologists.

The predictive coding framework offers a compelling model for temporal signal processing in the cortex. Recent studies explored its implementation in spiking architectures using Hebbian plasticity rules or offline learning; however, a biologically inspired model that enables gradient-based minimization of prediction errors remains an open challenge. In this work, we demonstrate that the predictive coding objective can be optimized using the online and local nature of the e-prop learning algorithm in recurrent spiking neural networks, creating the Predictive E-prop model. We demonstrate that the model is capable of learning complex time-series signals purely from self-supervised learning, using only its own prediction error as input, maintaining self-sustaining activity and reproducing the targets underlying dynamics even in the absence of external stimuli. Furthermore, Predictive E-prop shows robust signal reconstruction abilities, effectively filtering noise and successfully interpolating sparse data. A comparative study against a backpropagation-based approach reveals that the two achieve comparable performance after training, confirming the viability of our model for timeseries generation tasks. These findings are particularly relevant for future developments in neuromorphic hardware, offering a purely self-supervised, gradient-based model that could provide significant advantages in power efficiency and computational ability.

CROCOpy is a light-weighted toolbox for the assessment of neuronal oscillations, and multiple observables of functional connectivity (phase synchronization, amplitude coupling, and cross-frequency coupling) and critical dynamics (avalanches, long-range temporal correlations, bistability, and functional excitation-inhibition ratio). It was developed to simplify the analysis of continuous electrophysiological recordings and, in addition to metric computation, also includes methods for narrow-band filtering and statistical analysis. It is device-agnostic and supports both GPU and CPU computations. The toolbox also provides detailed tutorials.

Background: Paediatric pneumonia is a leading cause of childhood morbidity and mortality worldwide. Chest X-rays (CXR) are an important diagnostic tool in the diagnosis of pneumonia, but shortages in specialist radiology services lead to clinically significant delays in CXR reporting. The ability to communicate findings both to clinicians and laypersons allows MLLMs to be deployed throughout clinical workflows, from image analysis to patient communication. However, MLLMs currently underperform state-of-the-art deep learning classifiers. Objective: To evaluate the diagnostic accuracy of ensemble strategies with MLLMs compared to the baseline average agent for paediatric radiological pneumonia detection. Methods: We conducted a retrospective cohort study using paediatric CXRs from two independent hospital datasets totalling 2300 CXRs. Fifteen MedGemma-4B-it agents independently classified each CXR into five pneumonia likelihood categories. Majority voting, soft voting, and GPTOSS-20B aggregation were compared against the average agent performance. The primary metric evaluated was OvR AUROC. Secondary metrics included accuracy, sensitivity, specificity, F1-score, Cohen's kappa, and OvO AUROC. Results: Soft voting achieved improvements in OvR AUROC (p_balanced = 0.0002, p_real-world = 0.0003), accuracy (p_balanced = 0.0008, p_real-world < 0.0001), Cohen's Kappa (p_balanced = 0.0006, p_real-world = 0.0054) and OvO AUROC (p_balanced < 0.0001, p_real-world = 0.0011) across both datasets, and a superior F1-value (pbalanced = 0.0028) for the balanced dataset. Conclusion: Soft voting enhances MedGemma's diagnostic discriminatory performance for paediatric radiological pneumonia detection. Our system enables privacy-preserving, near real-time clinical decision support with explainable outputs, having potential for integration into emergency departments. Our system's high specificity supports triage by flagging high-risk radiological pneumonia cases.

Convolutional neural networks (CNNs) have become essential models for predicting neural activity and behavior in visual tasks. However, their ability to capture higher-level cognitive functions, such as numerosity discrimination, remains debated. Numerosity, the ability to perceive and estimate the number of items in a visual scene, is often proposed to rely on specialized number-detector units within CNNs, analogous to number-selective neurons observed in the brain. In this study, we use CORnet, a biologically inspired CNN architecture inspired by the organization of the primate visual system. To address a limitation of classical Representational Similarity Analysis (RSA)--its assumption that all units contribute equally--we apply pruning, a feature selection approach that identifies the units most relevant for explaining behavioral similarity structure. Our results show that number-detector units are not critical for population-level representations of numerosity, challenging their proposed role in previous studies.